In this work we present an explainable system for emotion attribution and recommendation (called DEGARI) relying on a recently introduced commonsense reasoning framework (the TCL logic) which is based on a human-like procedure for the automatic generation of novel concepts in a Description Logics knowledge base. Starting from an ontological formalization of emotions (known as ArsEmotica), the system exploits the logic TCL to automatically generate novel commonsense semantic representations of compound emotions (e.g. Love as derived from the combination of Joy and Trust according to the ArsEmotica model). The generated emotions correspond to prototypes, i.e. commonsense representations of given concepts, and have been used to reclassify emotion-related contents in a variety of artistic domains, ranging from art datasets to the editorial content available in RaiPlay, the online multimedia platform of RAI Radiotelevisione Italiana (the Italian public broadcasting company). We have tested our system (1) by reclassifying the available contents in the tested dataset with respect to the new generated compound emotions (2) with an evaluation, in the form of a controlled user study experiment, of the feasibility of using the obtained reclassifications as recommended emotional content. The obtained results are encouraging and pave the way to many possible further improvements and research directions.

Amazon is making it easier to remember an event you don't want to miss. The Verge reports that Amazon has quietly introduced a hinted-at "tell me when" Alexa command that not only answers your question about an event, but sets a reminder when that event happens. If you ask Alexa to "tell me when the Super Bowl is," your Echo or a similar device will both answer the question (February 7th, 2021, for the record) and alert you that day. You can also use "tell me when" for things like TV show air dates, holidays, or emails from contacts. The feature is only available for Alexa users in the US at present.

It's been a busy few weeks here at Engadget. In addition to celebrating the holidays, ringing in the New Year and prepping for next week's virtual CES, we've kept reviewing all the new gadgets and components that we can get our hands on. We start off with the long-awaited Apple AirPods Max headphones and, more recently, the Amazon Echo Frames which are now finally available. We also checked out Sony's portable A7C camera, HP's Reverb G2 mixed reality headset, NVIDIA's RTX 3060 Ti and the flexible Hologram Electronics Microcosm effects pedal. Long-rumored and quietly revealed last month, the AirPods Max are high-end, over-ear headphones constructed from aluminum and metal and available in five colors.

Users install many apps on their smartphones, raising issues related to information overload for users and resource management for devices. Moreover, the recent increase in the use of personal assistants has made mobile devices even more pervasive in users' lives. This paper addresses two research problems that are vital for developing effective personal mobile assistants: target apps selection and recommendation. The former is the key component of a unified mobile search system: a system that addresses the users' information needs for all the apps installed on their devices with a unified mode of access. The latter, instead, predicts the next apps that the users would want to launch. Here we focus on context-aware models to leverage the rich contextual information available to mobile devices. We design an in situ study to collect thousands of mobile queries enriched with mobile sensor data (now publicly available for research purposes). With the aid of this dataset, we study the user behavior in the context of these tasks and propose a family of context-aware neural models that take into account the sequential, temporal, and personal behavior of users. We study several state-of-the-art models and show that the proposed models significantly outperform the baselines.

Providing personalized explanations for recommendations can help users to understand the underlying insight of the recommendation results, which is helpful to the effectiveness, transparency, persuasiveness and trustworthiness of recommender systems. Current explainable recommendation models mostly generate textual explanations based on pre-defined sentence templates. However, the expressiveness power of template-based explanation sentences are limited to the pre-defined expressions, and manually defining the expressions require significant human efforts. Motivated by this problem, we propose to generate free-text natural language explanations for personalized recommendation. In particular, we propose a hierarchical sequence-to-sequence model (HSS) for personalized explanation generation. Different from conventional sentence generation in NLP research, a great challenge of explanation generation in e-commerce recommendation is that not all sentences in user reviews are of explanation purpose. To solve the problem, we further propose an auto-denoising mechanism based on topical item feature words for sentence generation. Experiments on various e-commerce product domains show that our approach can not only improve the recommendation accuracy, but also the explanation quality in terms of the offline measures and feature words coverage. This research is one of the initial steps to grant intelligent agents with the ability to explain itself based on natural language sentences.

Earlier today, Sony announced plans to expand its 360 Reality Audio platform. The key updates were a two-fold approach for expanding the limited content library, licensing tech to other companies and -- most importantly -- news that it would ship its own speakers built for the immersive sound this spring. At the time, the company said it didn't have any info beyond a few vague details, but that's wasn't entirely true. Sony's UK website has already posted full details for both the SRS-RA5000 and SRS-RA3000 "premium wireless speakers." If you've been following our 360 Reality Audio coverage since 2019, you'll recognize the designs.

Beijing – Browsing the internet as a young policeman in China, Ma Baoli recalls the sheer volume of web pages telling him he was a pervert, diseased and in need of treatment -- simply because he is gay. "I felt extremely lonely after I became aware of my sexual orientation," says Ma, at the time a newly minted officer in a small coastal city. Two decades later, the softly spoken 43-year-old now helms Blued, one of the world's largest dating platforms for gay men. The app went public last July with an $85 million debut on Nasdaq, a remarkable tech success story from a country that classified homosexuality as a mental illness as recently as 2001. Parent company BlueCity's sunlit Beijing campus teems with young and casually dressed programmers who hold meetings in rooms named after Oscar Wilde and other prominent LGBTQ figures from around the world.

Seven years after introducing webOS as the platform for its Smart TV lineup, LG is introducing version 6.0 with a new look and feel for its 2021 4K and 8K TVs. The old blade lineup of apps is gone, with a more modern tile-based layout. LG Home Entertainment president Park Hyoung-sei calls this "the most significant update since we first introduced webOS in 2014." An upgraded version of its ThinQ AI has more voice command control than ever whether you're using Google Assistant or Amazon Alexa. For traditional control, this year's edition of its Magic Remote is a bit more standard than some of the previous versions, but also includes NFC for the first time, which allows users to share content from phone to TV (and back) simply by tapping it.

Recommender systems play a crucial role in helping users to find their interested information in various web services such as Amazon, YouTube, and Google News. Various recommender systems, ranging from neighborhood-based, association-rule-based, matrix-factorization-based, to deep learning based, have been developed and deployed in industry. Among them, deep learning based recommender systems become increasingly popular due to their superior performance. In this work, we conduct the first systematic study on data poisoning attacks to deep learning based recommender systems. An attacker's goal is to manipulate a recommender system such that the attacker-chosen target items are recommended to many users. To achieve this goal, our attack injects fake users with carefully crafted ratings to a recommender system. Specifically, we formulate our attack as an optimization problem, such that the injected ratings would maximize the number of normal users to whom the target items are recommended. However, it is challenging to solve the optimization problem because it is a non-convex integer programming problem. To address the challenge, we develop multiple techniques to approximately solve the optimization problem. Our experimental results on three real-world datasets, including small and large datasets, show that our attack is effective and outperforms existing attacks. Moreover, we attempt to detect fake users via statistical analysis of the rating patterns of normal and fake users. Our results show that our attack is still effective and outperforms existing attacks even if such a detector is deployed.

Have an idle laptop sitting on your desk on a kitchen counter? Lenovo has a novel idea: Turn it into an Amazon Echo Show, complete with Alexa. Slated to debut on various Lenovo Yoga and IdeaPad laptops later this year, Lenovo's Show Mode brings the Echo Show interface to a Lenovo PC, complete with support for voice commands and smart home control. With Show Mode enabled, a Lenovo laptop or desktop system would essentially act as an Echo Show smart display. Just as with a standard Echo Show, you could ask Alexa questions, command her to turn your lights on and off, get weather reports, play music, read your schedule, or make calls to other Echo speakers.